A Performance Estimator for Parallel Programs

Abstract

In this paper we describe a Parallel Performance Estimator suitable for the comparative evaluation of parallel algorithms. The Estimator is designed for SPMD programs written in either C or FORTRAN. Simulation is used to produce estimates of execution times for varying numbers of processors and to analyse the communication overheads. Results from the estimator are compared with actual results (obtained on a 16 processor IBM SP2 machine) for an Alternating Direction Implicit (ADI) solver of linear equations and for a Parallel Sort by Regular Sampling (PSRS) sorting program. In both cases the plots of Execution Time versus Number of Processors are accurate to 20% and show all of the features of the equivalent plots of the measured data.